• Publications
  • Influence
ATOMIC: An Atlas of Machine Commonsense for If-Then Reasoning
TLDR
Experimental results demonstrate that multitask models that incorporate the hierarchical structure of if-then relation types lead to more accurate inference compared to models trained in isolation, as measured by both automatic and human evaluation. Expand
COMET: Commonsense Transformers for Automatic Knowledge Graph Construction
TLDR
This investigation reveals promising results when implicit knowledge from deep pre-trained language models is transferred to generate explicit knowledge in commonsense knowledge graphs, and suggests that using generative commonsense models for automatic commonsense KB completion could soon be a plausible alternative to extractive methods. Expand
Social IQA: Commonsense Reasoning about Social Interactions
TLDR
It is established that Social IQa, the first large-scale benchmark for commonsense reasoning about social situations, is challenging for existing question-answering models based on pretrained language models, compared to human performance (>20% gap). Expand
The Risk of Racial Bias in Hate Speech Detection
TLDR
This work proposes *dialect* and *race priming* as ways to reduce the racial bias in annotation, showing that when annotators are made explicitly aware of an AAE tweet’s dialect they are significantly less likely to label the tweet as offensive. Expand
Event2Mind: Commonsense Inference on Events, Intents, and Reactions
TLDR
It is demonstrated how commonsense inference on people’s intents and reactions can help unveil the implicit gender inequality prevalent in modern movie scripts. Expand
Social Bias Frames: Reasoning about Social and Power Implications of Language
TLDR
It is found that while state-of-the-art neural models are effective at high-level categorization of whether a given statement projects unwanted social bias, they are not effective at spelling out more detailed explanations in terms of Social Bias Frames. Expand
RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models
TLDR
It is found that pretrained LMs can degenerate into toxic text even from seemingly innocuous prompts, and empirically assess several controllable generation methods find that while data- or compute-intensive methods are more effective at steering away from toxicity than simpler solutions, no current method is failsafe against neural toxic degeneration. Expand
Psychological Language on Twitter Predicts County-Level Heart Disease Mortality
TLDR
Capturing community psychological characteristics through social media is feasible, and these characteristics are strong markers of cardiovascular mortality at the community level. Expand
Developing Age and Gender Predictive Lexica over Social Media
TLDR
Predictive lexica (words and weights) for age and gender using regression and classification models from word usage in Facebook, blog, and Twitter data with associated demographic labels achieve state-of-the-art accuracy. Expand
The Effect of Different Writing Tasks on Linguistic Style: A Case Study of the ROC Story Cloze Task
TLDR
It is shown how variants of the same writing task can lead to measurable differences in writing style, and a simple linear classifier informed by stylistic features is able to successfully distinguish among the three cases. Expand
...
1
2
3
4
...